AI Paper Atlas

Research map / Video / Video-language understanding

The SA-FARI Dataset: Segment Anything in Footage of Animals for Recognition and Identification

Dante Wasmuht, Otto Brookes, Maximilian Schall, Pablo Palencia, Christopher Beirne, Tilo Burghardt, Majid Mirmehdi, Hjalmar Kühl, Mimi Arandjelovic, Sam Pottie, Peter Bermant, Brandon Asheim and 12 more

CVPR 2026 · Video › Video-language understanding · approach: Event and anomaly reasoning in video · 5 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add SA-FARI data proportionally into SAM 3 trainingSAM 3 · SA-FARI test (species-specific)cgF1: 14.0 -> 39.0Improved
add SA-FARI data proportionally into SAM 3 trainingSAM 3 · SA-FARI test (species-specific)pHOTA Total: 48.5 -> 63.1Improved
explicitly fine-tune SAM 3 on SA-FARISAM 3 · SA-FARI test (species-specific)cgF1: 14.0 -> 46.9Improved
explicitly fine-tune SAM 3 on SA-FARISAM 3 · SA-FARI test (species-specific)pHOTA Total: 48.5 -> 68.1Improved
explicitly fine-tune SAM 3 on SA-FARISAM 3 · SA-FARI test (species-specific)TETA: 39.6 -> 58.7Improved
fine-tune rather than mix SA-FARI into trainingSAM 3 (SA-FARI) · SA-FARI test (species-specific)cgF1: 39.0 -> 46.9Improved
use SAM 3 detector-tracker instead of LLMDet with trackerLLMDet + SAM 3 TR · SA-FARI test (species-specific)cgF1: 2.6 -> 14.0Improved
replace MegaDetector + tracker with SAM 3 trained on SA-FARIMD+BoostSort++ · SA-FARI test (species-agnostic)IDF1: 47.2 -> 71.1Improved
replace MegaDetector + OCSort with SAM 3 trained on SA-FARIMD+OCSort · SA-FARI test (species-agnostic)HOTA Total: 45.5 -> 64.4Improved
small instead of large masklets in test videosSAM 3 FT (SA-FARI) · SA-FARI test subsetspHOTA Total: 81.4 -> 52.2Hurt
challenging videos (occlusion, motion) vs overall setSAM 3 FT (SA-FARI) · SA-FARI test subsetspHOTA Ass: 84.6 -> 75.3Hurt
night videos vs overall setSAM 3 FT (SA-FARI) · SA-FARI test subsetspHOTA Total: 68.1 -> 66.0Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy